Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1678 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.6943. Min Act: -0.1700

Data Index: 872634 (Open Web Text)

Max Activating Token Index: 112

Text #1

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.6177. Min Act: -0.1700

Data Index: 5186033 (Open Web Text)

Max Activating Token Index: 887

Text #2

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.6010. Min Act: -0.1700

Data Index: 6064384 (Open Web Text)

Max Activating Token Index: 75

Text #3

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5535. Min Act: -0.1700

Data Index: 7811385 (Open Web Text)

Max Activating Token Index: 363

Text #4

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4614. Min Act: -0.1700

Data Index: 8125316 (Open Web Text)

Max Activating Token Index: 873

Text #5

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4915. Min Act: -0.1700

Data Index: 3168636 (Open Web Text)

Max Activating Token Index: 468

Text #6

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5309. Min Act: -0.1700

Data Index: 3729387 (Open Web Text)

Max Activating Token Index: 677

Text #7

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.5061. Min Act: -0.1700

Data Index: 2446978 (Open Web Text)

Max Activating Token Index: 468

Text #8

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4796. Min Act: -0.1700

Data Index: 1400746 (Open Web Text)

Max Activating Token Index: 185

Text #9

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4893. Min Act: -0.1700

Data Index: 2684544 (Open Web Text)

Max Activating Token Index: 111

Text #10

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4907. Min Act: -0.1700

Data Index: 8785660 (Open Web Text)

Max Activating Token Index: 813

Text #11

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4580. Min Act: -0.1700

Data Index: 3772590 (Open Web Text)

Max Activating Token Index: 81

Text #12

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4359. Min Act: -0.1700

Data Index: 6646115 (Open Web Text)

Max Activating Token Index: 158

Text #13

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3925. Min Act: -0.1700

Data Index: 3803616 (Open Web Text)

Max Activating Token Index: 514

Text #14

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.4283. Min Act: -0.1700

Data Index: 727793 (Open Web Text)

Max Activating Token Index: 174

Text #15

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3654. Min Act: -0.1700

Data Index: 5832763 (Open Web Text)

Max Activating Token Index: 415

Text #16

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3223. Min Act: -0.1700

Data Index: 5157287 (Open Web Text)

Max Activating Token Index: 540

Text #17

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3016. Min Act: -0.1700

Data Index: 1482645 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3174. Min Act: -0.1700

Data Index: 2766273 (Open Web Text)

Max Activating Token Index: 651

Text #19

Max Range: 4.6943. Min Range: -4.6943

Max Act: 4.3056. Min Act: -0.1700

Data Index: 4863715 (Open Web Text)

Max Activating Token Index: 16